Data Scientist turning raw data into strategic business decisions through machine learning, predictive modeling, and clear data storytelling.
Programming & Data Tools: Python (Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn), SQL, Power BI, Advanced Excel (Pivot Tables, VLOOKUP, Power Pivot), Git/GitHub
Core Competencies: Data Cleaning & Wrangling, Exploratory Data Analysis, Statistical Analysis, Machine Learning (Supervised & Unsupervised), Feature Engineering, Model Evaluation, Predictive Modeling, Data Visualization, Dashboard Development, Data Storytelling
I'm a data scientist specializing in machine learning and predictive modeling, with a strong foundation in SQL, Python, Power BI, and Excel. I help organizations move from raw, disconnected data to clear, actionable insight, building clean pipelines, uncovering patterns through exploratory analysis, and translating statistical findings into decisions leadership can act on with confidence.
Comprehensive diagnostic analysis of retail enterprise transactional log architecture to discover buying patterns and optimize multi-channel performance metrics.
A multi-page Power BI dashboard connecting billing, network performance, and support tickets to one customer record, uncovering churn drivers and quantifying revenue tied to service failures.
An end-to-end relational database pipeline modeling complete patient tracking logs, clinical metrics, and finance auditing schemas using SQL server structures.
A relational data pipeline built in Python and Pandas auditing, cleaning, and enriching four travel files to track unbilled revenue leaks.
A nine-table Power BI model with 14 DAX measures tracking production efficiency, cost and scrap, machine downtime, order fulfilment and supplier performance.
An end-to-end Python pipeline that cleans five messy travel tables, builds a star schema, answers five business objectives with charts, and trains models for cancellations, trip cost, policy compliance, support escalation and billing anomalies.